© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6253
    Prev
    Next
    INDEX
    Explanations

    the word "pretty" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.59
    sizeCache
    -0.52
    exels
    -0.47
    IActionResult
    -0.47
    MockBean
    -0.45
     defaultstate
    -0.45
     wastage
    -0.44
     AssemblyCulture
    -0.44
     hermanas
    -0.43
    どうか
    -0.43
    POSITIVE LOGITS
     pretty
    2.75
    pretty
    2.56
    Pretty
    2.44
     Pretty
    2.36
     PRET
    1.56
     ziemlich
    1.31
    PRET
    1.23
     fairly
    1.21
     bastante
    1.19
     prettiest
    1.17
    Activations Density 0.103%

    No Known Activations